[PATCH v2 2/2] mm: speed up mremap by 500x on large regions

[Kirill A. Shutemov]

On Fri, Oct 12, 2018 at 05:42:24PM +0100, Anton Ivanov wrote:
> 
> On 10/12/18 3:48 PM, Anton Ivanov wrote:
> > On 12/10/2018 15:37, Kirill A. Shutemov wrote:
> > > On Fri, Oct 12, 2018 at 03:09:49PM +0100, Anton Ivanov wrote:
> > > > On 10/12/18 2:37 AM, Joel Fernandes (Google) wrote:
> > > > > Android needs to mremap large regions of memory during
> > > > > memory management
> > > > > related operations. The mremap system call can be really
> > > > > slow if THP is
> > > > > not enabled. The bottleneck is move_page_tables, which is copying each
> > > > > pte at a time, and can be really slow across a large map.
> > > > > Turning on THP
> > > > > may not be a viable option, and is not for us. This patch
> > > > > speeds up the
> > > > > performance for non-THP system by copying at the PMD level
> > > > > when possible.
> > > > > 
> > > > > The speed up is three orders of magnitude. On a 1GB mremap, the mremap
> > > > > completion times drops from 160-250 millesconds to 380-400
> > > > > microseconds.
> > > > > 
> > > > > Before:
> > > > > Total mremap time for 1GB data: 242321014 nanoseconds.
> > > > > Total mremap time for 1GB data: 196842467 nanoseconds.
> > > > > Total mremap time for 1GB data: 167051162 nanoseconds.
> > > > > 
> > > > > After:
> > > > > Total mremap time for 1GB data: 385781 nanoseconds.
> > > > > Total mremap time for 1GB data: 388959 nanoseconds.
> > > > > Total mremap time for 1GB data: 402813 nanoseconds.
> > > > > 
> > > > > Incase THP is enabled, the optimization is skipped. I also flush the
> > > > > tlb every time we do this optimization since I couldn't find a way to
> > > > > determine if the low-level PTEs are dirty. It is seen that the cost of
> > > > > doing so is not much compared the improvement, on both
> > > > > x86-64 and arm64.
> > > > > 
> > > > > Cc: minchan at kernel.org
> > > > > Cc: pantin at google.com
> > > > > Cc: hughd at google.com
> > > > > Cc: lokeshgidra at google.com
> > > > > Cc: dancol at google.com
> > > > > Cc: mhocko at kernel.org
> > > > > Cc: kirill at shutemov.name
> > > > > Cc: akpm at linux-foundation.org
> > > > > Signed-off-by: Joel Fernandes (Google) <joel at joelfernandes.org>
> > > > > ---
> > > > >    mm/mremap.c | 62
> > > > > +++++++++++++++++++++++++++++++++++++++++++++++++++++
> > > > >    1 file changed, 62 insertions(+)
> > > > > 
> > > > > diff --git a/mm/mremap.c b/mm/mremap.c
> > > > > index 9e68a02a52b1..d82c485822ef 100644
> > > > > --- a/mm/mremap.c
> > > > > +++ b/mm/mremap.c
> > > > > @@ -191,6 +191,54 @@ static void move_ptes(struct
> > > > > vm_area_struct *vma, pmd_t *old_pmd,
> > > > >            drop_rmap_locks(vma);
> > > > >    }
> > > > > +static bool move_normal_pmd(struct vm_area_struct *vma,
> > > > > unsigned long old_addr,
> > > > > +          unsigned long new_addr, unsigned long old_end,
> > > > > +          pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
> > > > > +{
> > > > > +    spinlock_t *old_ptl, *new_ptl;
> > > > > +    struct mm_struct *mm = vma->vm_mm;
> > > > > +
> > > > > +    if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK)
> > > > > +        || old_end - old_addr < PMD_SIZE)
> > > > > +        return false;
> > > > > +
> > > > > +    /*
> > > > > +     * The destination pmd shouldn't be established, free_pgtables()
> > > > > +     * should have release it.
> > > > > +     */
> > > > > +    if (WARN_ON(!pmd_none(*new_pmd)))
> > > > > +        return false;
> > > > > +
> > > > > +    /*
> > > > > +     * We don't have to worry about the ordering of src and dst
> > > > > +     * ptlocks because exclusive mmap_sem prevents deadlock.
> > > > > +     */
> > > > > +    old_ptl = pmd_lock(vma->vm_mm, old_pmd);
> > > > > +    if (old_ptl) {
> > > > > +        pmd_t pmd;
> > > > > +
> > > > > +        new_ptl = pmd_lockptr(mm, new_pmd);
> > > > > +        if (new_ptl != old_ptl)
> > > > > +            spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
> > > > > +
> > > > > +        /* Clear the pmd */
> > > > > +        pmd = *old_pmd;
> > > > > +        pmd_clear(old_pmd);
> > > > > +
> > > > > +        VM_BUG_ON(!pmd_none(*new_pmd));
> > > > > +
> > > > > +        /* Set the new pmd */
> > > > > +        set_pmd_at(mm, new_addr, new_pmd, pmd);
> > > > UML does not have set_pmd_at at all
> > > Every architecture does. :)
> > 
> > I tried to build it patching vs 4.19-rc before I made this statement and
> > ran into that.
> > 
> > Presently it does not.
> > 
> > https://elixir.bootlin.com/linux/v4.19-rc7/ident/set_pmd_at - UML is not
> > on the list.
> 
> Once this problem as well as the omissions in the include changes for UML in
> patch one have been fixed it appears to be working.
> 
> What it needs is attached.

Well, the optization is only suitable for arch that has 3 or more levels
of page tables. Otherwise it will not have [non-folded] pmd.

And in this case arch/um already should have set_pmd_at(), see
3_LEVEL_PGTABLES.

To port on 2-level paging, it has to be handled on pgd level. It
complicates the code and will not bring much value.

-- 
 Kirill A. Shutemov